semantictext 0.2.0 → 0.2.1

data/CHANGELOG.rdoc

@@ -0,0 +1,11 @@
+== CHANGELOG
+   
+=== 0.2.1 
+    2009-12-05: added support for multi-level headings e.g. "!!second level heading"
+
+=== 0.2.0
+    2009-12-03: replaced ST::Link with ST::HttpTag, ST::MailToTag and ST::FtpTag
+    2009-12-02: renamed SemanticText::Parser to SemanticText::Document
+    2009-12-02: added support for arbitrary tags
+=== 0.0.1
+

data/README.rdoc

@@ -1,10 +1,10 @@
-= Semantic Text
+== Semantic Text
 Semantic Text is a Domain-Specific text markup parser. 
 It takes a file or sequence of lines and returns an object model of the document, 
 including document metadata (e.g. doc creation time and title) and a tree of 
 interconnected objects describing the document structure.
 
-= How to use it
+=== How to use it
 * You need to have installed gemcutter.org into your gem locations.
 * Install with:
    gem install semantictext
@@ -27,8 +27,9 @@ interconnected objects describing the document structure.
     
 * *rdoc* http://www.greenbarsoft.co.uk/software/semantictext/rdoc/
 * *source* http://github.com/dafydd/semantictext 
+* To build me, set an environment variable called *SANDBOX* to the directory above your semantictext directory. The tests need this to access test data.
 
-= Semantic Markup
+=== Semantic Markup
 Semantic text supports:
 * document metadata 
 * section headers
@@ -36,15 +37,13 @@ Semantic text supports:
 * paragraphs that contain markup tags
 * inline hyperlinks for http: mailto: and ftp:
 * markup tags within bullet points
+* custom markup tags e.g. postal code, youtube video embed, ... whatever you define in a subclass of SemanticText::DefaultTagFactory
 
-We intend to support these features in future:
-* custom markup tags e.g. postal code, youtube video embed, ...
 
-
-= Compatibility
+=== Compatibility
 This project is being developed on OS X. Automated testing for Linux will be included in future releases.
  
-= Licence
+=== Licence
 This is open source software and comes with no warranty. See COPYING for details.
 
 http://www.greenbarsoft.co.uk

data/TODO.rdoc

@@ -1,7 +1,7 @@
 ==to do
-* support urls as a special structure tag
-* tighten up error test cases on ftptag, httptag and mailtotag
 * improve testing by mocking out tag factory used in tests - consider how/whether to do this
+* tighten up error test cases on ftptag, httptag and mailtotag
+* add verbatim code sections between {{{ and }}} brackets at start of line
 * support wikinames as a special custom tag
 * fix path to testfiles so test can run on gem - tests only run on source at the moment
 
@@ -12,6 +12,10 @@
 * pull out parsers for different parts and use the state pattern
 
 ==done
+* added basic rcov test coverage task to Rakefile
+* find a way to generate demo.txt file from rake
+* make demo.txt be up-to-date as dependency of rdoc
+* replace SemanticText::Link with SemanticText::HTTPTag, SemanticText::MailToTag and SemanticText::FTPTag
 * support custom structure tags
 * escape HTML < > and & on headings
 * build gem from rakefile

data/doc/demo.script

@@ -0,0 +1,13 @@
+require 'semantictext'
+
+p = SemanticText::Document.new
+p.parse 'title: my happy document'
+p.parse ''
+p.parse "!I'm a title"
+p.parse "I'm a paragraph..."
+p.parse "... yep, I'm still that paragraph."
+p.parse ''
+p.parse "* I'm a bullet point"
+p.parse "* I'm another bullet point"
+
+puts p.export_html           # this is how to export as a HTML fragment

data/lib/semantictext/default_tag_factory.rb

@@ -5,7 +5,7 @@ require 'semantictext/unknown_tag'
 
 module SemanticText
   # I create SemanticText::Tag objects in response to create_tag(name,value) calls 
-  # from a SemanticText::Parser
+  # from a SemanticText::Document
   class DefaultTagFactory
 
     def initialize()

data/lib/semantictext/document.rb

@@ -4,7 +4,6 @@ require 'semantictext/keyword_extractor'
 require 'semantictext/not_header_line'
 require 'semantictext/paragraph'
 require 'semantictext/span'
-require 'semantictext/link'
 require 'semantictext/tag'
 require 'string'
 require 'semantictext/bulletedlist'
@@ -108,7 +107,7 @@ module SemanticText
   	    return
       end
   		if (line.begins_with('!'))
-  			@content << Heading.new(line[1,line.size-1])
+  		  @content << Heading.parse(line)
   		else
   		  if (line.begins_with('*'))
   		    if @bulleted_list_parser.nil?

data/lib/semantictext/ftptag.rb

@@ -1,4 +1,5 @@
 require 'semantictext/tag'
+require 'semantictext/tag_parsing_failed'
 
 module SemanticText
   class FTPTag < Tag

data/lib/semantictext/heading.rb

@@ -1,14 +1,20 @@
 module SemanticText
   class Heading
-  	attr_reader :text
+  	attr_reader :text, :depth
 
-  	def initialize(aTitle)
+    def self.parse(line)
+      line =~ /(!+)(.*)/
+      Heading.new($2,$1.size)
+    end
+
+  	def initialize(aTitle, depth)
   		@text = aTitle
+  		@depth = depth
   	end
   	
   	#export as html
     def export_html
-      "\n<h1>#{ CGI.escapeHTML(@text)}</h1>"
+      "\n<h#{@depth}>#{ CGI.escapeHTML(@text)}</h#{@depth}>"
     end
     
   end

data/lib/semantictext/httptag.rb

@@ -9,6 +9,6 @@ module SemanticText
   		@key = key
   		@link = key+':'+value
   	end
-  	
+
   end
 end

data/lib/semantictext/mailtotag.rb

@@ -7,6 +7,7 @@ module SemanticText
     def initialize(key, value)
   		@text = value
   		@address = @value = value
+  		@key = key
   	end
   	
   end

data/lib/semantictext/rich_text_parser.rb

@@ -1,5 +1,4 @@
 require 'semantictext/span'
-require 'semantictext/link'
 require 'semantictext/tag'
 
 require 'string'
@@ -15,7 +14,15 @@ module SemanticText
       @tag_factory = tag_factory
     end
 
-  private
+    private
+  
+    def create_tag(regex, source)
+      source =~ regex
+      tag_name = $1
+      tag_value = $2
+      @tag_factory.create_tag(tag_name, tag_value)
+    end
+    
     def parse_text_for_urls(text, enclosing_element)
   	    link_next = false
   	    ignore_next_section = false
@@ -29,7 +36,7 @@ module SemanticText
   	          ignore_next_section = false
   	        else
   	          if (link_next)
-  	            enclosing_element << Link.new(section)
+  	            enclosing_element << create_tag(/([^:]+):([^\]]*)/, section)
   	            ignore_next_section = true            
   	          else
   	            enclosing_element << Span.new(section)
@@ -40,15 +47,14 @@ module SemanticText
   	end
 
     public
+    
+    # I parse a line of text, pushing the elements into enclosing_element as I find them.
     def parse(line, enclosing_element)
       sections = line.split /(\[[^:]+:[^\]]+\])/
       tag_next = false
       sections.each do |section|
         if (tag_next)
-          section  =~ /\[([^:]+):([^\]]*)\]/
-          tag_name = $1
-          tag_value = $2
-          enclosing_element << @tag_factory.create_tag(tag_name, tag_value)
+          enclosing_element << create_tag(/\[([^:]+):([^\]]*)\]/, section)
         else
           parse_text_for_urls(section, enclosing_element)
         end

data/lib/semantictext/tag.rb

@@ -9,9 +9,9 @@ module SemanticText
   		@key = key
   	end
   	
-    #export as html
-    def export_html
-      "[#{@key}:#{@text}]"
+  	# export as html
+  	def export_html
+      "<a href=\"#{key}:#{text}\">#{key}:#{CGI.escapeHTML(text)}</a>"
     end
     
   end

data/test/{bullet_test.rb → test_bullet.rb}

@@ -15,9 +15,9 @@ class BulletTest < Test::Unit::TestCase
 	  unit = SemanticText::Bullet.new(test_string, 1, SemanticText::RichTextParser.new(SemanticText::DefaultTagFactory.new))
 	  assert_equal(1, unit.depth)
 	  assert_element SemanticText::Span, "beginning ", unit.content[0]
-	  assert_element SemanticText::Link, "http://www.example.com", unit.content[1]
+	  assert_element SemanticText::HTTPTag, "//www.example.com", unit.content[1]
 	  assert_element SemanticText::Span, " moretext ", unit.content[2]
-	  assert_element SemanticText::Link, "http://www.dafydd.net", unit.content[3]
+	  assert_element SemanticText::HTTPTag, "//www.dafydd.net", unit.content[3]
 	  assert_element SemanticText::Span, " ending text", unit.content[4]
 	end
 

data/test/{parser_test.rb → test_document.rb}

@@ -1,7 +1,7 @@
 require 'test/unit'
 require 'semantictext/document' 
 
-class TestParser < Test::Unit::TestCase
+class TestDocument < Test::Unit::TestCase
 
 	def assert_element(element_class, text, actual)
 	  assert_equal element_class, actual.class
@@ -63,9 +63,9 @@ EOF
             test_lines.each {|line| unit.parse(line)}
             result = unit.content[0]
             assert_equal SemanticText::Paragraph, result.class
-            assert_element SemanticText::Link, "http://www.dafydd.net/foogoo?blah", result.content[0]
+            assert_element SemanticText::HTTPTag, "//www.dafydd.net/foogoo?blah", result.content[0]
             assert_element SemanticText::Span, " see? ", result.content[1]
-            assert_element SemanticText::Link, "http://www.example.com", result.content[2]
+            assert_element SemanticText::HTTPTag, "//www.example.com", result.content[2]
             assert_element SemanticText::Span, "I wonder if it worked!", result.content[3]
             assert_equal 4, result.content.size    
     end
@@ -76,20 +76,20 @@ EOF
 
 Embedded link http://www.dafydd.net/foogoo?blah see?
 I wonder if it worked!
-a mailto:foogoo b ftp://asdfasdfasdf c
+a mailto:foogoo b ftp://host/path c
 EOF
       test_lines.each {|line| unit.parse(line)}
 
       result = unit.content[0]
       assert_equal SemanticText::Paragraph, result.class
       assert_element SemanticText::Span, "Embedded link ", result.content[0]
-      assert_element SemanticText::Link, "http://www.dafydd.net/foogoo?blah", result.content[1]
+      assert_element SemanticText::HTTPTag, "//www.dafydd.net/foogoo?blah", result.content[1]
       assert_element SemanticText::Span, " see?", result.content[2]
       assert_element SemanticText::Span, "I wonder if it worked!", result.content[3]
       assert_element SemanticText::Span, 'a ', result.content[4]
-      assert_element SemanticText::Link, 'mailto:foogoo', result.content[5]
+      assert_element SemanticText::MailToTag, 'foogoo', result.content[5]
       assert_element SemanticText::Span, ' b ', result.content[6]
-      assert_element SemanticText::Link, 'ftp://asdfasdfasdf', result.content[7]
+      assert_element SemanticText::FTPTag, '//host/path', result.content[7]
       assert_element SemanticText::Span, ' c', result.content[8]
       assert_equal 9, result.content.size
   	end
@@ -176,6 +176,31 @@ EOF
         assert_equal 9, result.content.size
     	end
 
+  def test_heading_parsing
+    unit = SemanticText::Document.new
+    unit.parse ''
+    unit.parse '!1st level heading'
+    unit.parse '!!2nd level heading'
+    unit.parse '!!!3rd level heading'
+    
+    first_heading = unit.content[0]
+    second_heading = unit.content[1]
+    third_heading = unit.content[2]
+    
+    assert_equal "1st level heading", first_heading.text
+    assert_equal SemanticText::Heading, first_heading.class
+    assert_equal 1, first_heading.depth
+    
+    
+    assert_equal "2nd level heading", second_heading.text
+    assert_equal SemanticText::Heading, second_heading.class
+    assert_equal 2, second_heading.depth
+    
+    assert_equal "3rd level heading", third_heading.text
+    assert_equal SemanticText::Heading, third_heading.class
+    assert_equal 3, third_heading.depth
+  end
+  
 	def test_paragraphs_headings_and_bullet_points
     unit = SemanticText::Document.new
     unit.parse('')
@@ -231,7 +256,7 @@ EOF
     assert_equal SemanticText::BulletedList, actual_list.class
 
     assert_element SemanticText::Span, 'with url ', first_bullet.content[0]
-    assert_element SemanticText::Link, 'http://www.example.com', first_bullet.content[1]
+    assert_element SemanticText::HTTPTag, '//www.example.com', first_bullet.content[1]
     assert_element SemanticText::Span, ' see?', first_bullet.content[2]
 
     assert_element SemanticText::Span, 'with tag ', second_bullet.content[0]

data/test/{export_test.rb → test_export.rb}

@@ -13,6 +13,8 @@ class TestExport < Test::Unit::TestCase
     expected = expected_file.readlines
     
     (0..(expected.size-1)).each {|index| assert_equal expected[index],actual[index]+"\n"}
+    
+    assert_equal expected.size, actual.size
   end
   
   def test_escaping_paragraphs

data/testfiles/complex.art

@@ -11,6 +11,9 @@ This paragraph tests escaping < > &
 
 Theis is the third paragraph.
 
+!!second-level heading
+!!!third-level heading
+
 Hey dude, check out my website: 
 http://www.example.com Cool innit?
 
@@ -26,3 +29,7 @@ http://www.example.com Cool innit?
 This is another paragraph. This is a [http://www.example.com] tag.
 
 http://www.example.com/foo?a=b&c=d
+
+ftp://host/path
+
+mailto:fred@example.com

data/testfiles/regression-exportsample.txt

@@ -3,6 +3,8 @@
 <p> This is another paragraph.</p>
 <p> This paragraph tests escaping &lt; &gt; &amp;</p>
 <p> Theis is the third paragraph.</p>
+<h2>second-level heading</h2>
+<h3>third-level heading</h3>
 <p> Hey dude, check out my website: <a href="http://www.example.com">http://www.example.com</a>  Cool innit?</p>
 <h1>Second Big Section &lt; &gt; &amp;</h1>
 	<ul><li> point 1</li>
@@ -11,5 +13,7 @@
 		<ul><li> subpoint 2.1</li><li> subpoint 2.2</li>
 		</ul>
 	</ul>
-<p> This is another paragraph. This is a [http://www.example.com]  tag.</p>
+<p> This is another paragraph. This is a <a href="http://www.example.com">http://www.example.com</a>  tag.</p>
 <p><a href="http://www.example.com/foo?a=b&c=d">http://www.example.com/foo?a=b&amp;c=d</a></p>
+<p><a href="ftp://host/path">ftp://host/path</a></p>
+<p><a href="mailto:fred@example.com">mailto:fred@example.com</a></p>

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: semantictext
 version: !ruby/object:Gem::Version 
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors: 
 - Dafydd Rees
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-02 00:00:00 +00:00
+date: 2009-12-05 00:00:00 +00:00
 default_executable: 
 dependencies: []
 
@@ -20,11 +20,12 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
-- CHANGELOG
+- CHANGELOG.rdoc
 - COPYING
 - README.rdoc
 - TODO.rdoc
 files: 
+- doc/demo.script
 - lib/semantictext/bullet.rb
 - lib/semantictext/bulleted_list_parser.rb
 - lib/semantictext/bulletedlist.rb
@@ -36,7 +37,6 @@ files:
 - lib/semantictext/heading.rb
 - lib/semantictext/httptag.rb
 - lib/semantictext/keyword_extractor.rb
-- lib/semantictext/link.rb
 - lib/semantictext/mailtotag.rb
 - lib/semantictext/not_header_line.rb
 - lib/semantictext/paragraph.rb
@@ -47,17 +47,17 @@ files:
 - lib/semantictext/unknown_tag.rb
 - lib/semantictext.rb
 - lib/string.rb
-- test/bullet_test.rb
-- test/bulleted_list_parser_test.rb
-- test/dateextractor_test.rb
-- test/default_tag_factory_test.rb
-- test/export_test.rb
-- test/keywordextractor_test.rb
-- test/parser_test.rb
+- test/test_bullet.rb
+- test/test_bulleted_list_parser.rb
+- test/test_dateextractor.rb
+- test/test_default_tag_factory.rb
+- test/test_document.rb
+- test/test_export.rb
+- test/test_keywordextractor.rb
 - testfiles/complex.art
 - testfiles/regression-exportsample.txt
 - testfiles/simple.art
-- CHANGELOG
+- CHANGELOG.rdoc
 - COPYING
 - README.rdoc
 - TODO.rdoc
@@ -90,10 +90,10 @@ signing_key:
 specification_version: 3
 summary: Domain-Specific text markup parser
 test_files: 
-- ./test/bullet_test.rb
-- ./test/bulleted_list_parser_test.rb
-- ./test/dateextractor_test.rb
-- ./test/default_tag_factory_test.rb
-- ./test/export_test.rb
-- ./test/keywordextractor_test.rb
-- ./test/parser_test.rb
+- ./test/test_bullet.rb
+- ./test/test_bulleted_list_parser.rb
+- ./test/test_dateextractor.rb
+- ./test/test_default_tag_factory.rb
+- ./test/test_document.rb
+- ./test/test_export.rb
+- ./test/test_keywordextractor.rb

data/CHANGELOG

@@ -1,2 +0,0 @@
-2009-12-02: renamed SemanticText::Parser to SemanticText::Document
-2009-12-02: added support for arbitrary tags

data/lib/semantictext/link.rb

@@ -1,9 +0,0 @@
-require 'cgi'
-module SemanticText
-  class Link < Span
-    # export as html
-    def export_html
-      "<a href=\"#{text}\">#{CGI.escapeHTML(text)}</a>"
-    end
-  end
-end